Repository navigation
可以直接跳过微调启动模型,查看效果吗?希望可以更详细的步骤介绍 #112
Description

Activity
data_stats_path是指什么的路径?传入前面下载的LIBERO数据集路径可以吗
- If you have AgiBot G1, you can directly deploy GO-1. Otherwise, you need to finetune on your dataset first.
- When finetuning GO-1, data_stats is automatically saved alongside your checkpoint. Pass this file when deploying.
Could you explain what each parameter in the payload? Or where can I learn about them?
By default, the model takes three images, one instruction, and robot state (proprioception) as input to output actions. Different LeRobot datasets use different image key names (e.g., "image", "head_color"), which need to be specified in the config. You can also use fewer than 3 images, as shown in our Libero example. The
ctrl_freqsparameter sets the robot control frequency - use the default value of 30 if unsure.payload = { "top": np.array(Image.open("frames/head_color.mp4_20251011_194851.031.png").convert("RGB")), "right": np.array(Image.open("frames/hand_right_color.mp4_20251011_194816.624.png").convert("RGB")), "left": np.array(Image.open("frames/hand_left_color.mp4_20251011_194739.489.png").convert("RGB")), "instruction": "Hanging clothes with a hanger", "state": np.expand_dims(np.random.rand(16), axis=0), "ctrl_freqs": np.array([30]), }Reacted by Modi Shi and zbzyjyapayload = { "top": np.array(Image.open("frames/head_color.mp4_20251011_194851.031.png").convert("RGB")), "right": np.array(Image.open("frames/hand_right_color.mp4_20251011_194816.624.png").convert("RGB")), "left": np.array(Image.open("frames/hand_left_color.mp4_20251011_194739.489.png").convert("RGB")), "instruction": "Hanging clothes with a hanger", "state": np.expand_dims(np.random.rand(16), axis=0), "ctrl_freqs": np.array([30]), }Thank you for your response. If I want to directly test the effect of the original model, how should I implement video stream input using the payload example you provided, as well as the sequential execution of the robot after the action is returned? Are there any open-source projects or modules that I can refer to?